Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5643 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1733. Min Range: -5.1733
Max Act: 5.1733. Min Act: -0.1700
Data Index: 4012972 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1733. Min Range: -5.1733
Max Act: 5.1733. Min Act: -0.1700
Data Index: 1095952 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1733. Min Range: -5.1733
Max Act: 5.1108. Min Act: -0.1700
Data Index: 6046045 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1733. Min Range: -5.1733
Max Act: 5.1108. Min Act: -0.1700
Data Index: 1712511 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1733. Min Range: -5.1733
Max Act: 5.0795. Min Act: -0.1700
Data Index: 8156920 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1733. Min Range: -5.1733
Max Act: 5.0483. Min Act: -0.1700
Data Index: 8541683 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1733. Min Range: -5.1733
Max Act: 5.0170. Min Act: -0.1700
Data Index: 457866 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1733. Min Range: -5.1733
Max Act: 5.0170. Min Act: -0.1700
Data Index: 6511677 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1733. Min Range: -5.1733
Max Act: 4.9545. Min Act: -0.1700
Data Index: 3107319 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1733. Min Range: -5.1733
Max Act: 4.9858. Min Act: -0.1700
Data Index: 1692982 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1733. Min Range: -5.1733
Max Act: 4.9233. Min Act: -0.1700
Data Index: 5119802 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1733. Min Range: -5.1733
Max Act: 4.9545. Min Act: -0.1700
Data Index: 7929508 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1733. Min Range: -5.1733
Max Act: 4.9545. Min Act: -0.1700
Data Index: 115705 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1733. Min Range: -5.1733
Max Act: 4.9233. Min Act: -0.1700
Data Index: 981066 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1733. Min Range: -5.1733
Max Act: 4.9233. Min Act: -0.1700
Data Index: 3627895 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1733. Min Range: -5.1733
Max Act: 4.9233. Min Act: -0.1700
Data Index: 766935 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1733. Min Range: -5.1733
Max Act: 4.8608. Min Act: -0.1700
Data Index: 7229179 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1733. Min Range: -5.1733
Max Act: 4.8920. Min Act: -0.1700
Data Index: 475631 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1733. Min Range: -5.1733
Max Act: 4.8920. Min Act: -0.1700
Data Index: 2406106 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1733. Min Range: -5.1733
Max Act: 4.8920. Min Act: -0.1700
Data Index: 1671440 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #19